EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Lightweight Federated Learning Approach for Resource-Constrained Internet of Things

M Baqer iD

Sensors · 10.09.2025 · 25 (18) · 5633

DOI: 10.3390/s25185633 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.09.2025. Verfasst von M Baqer. Beteiligte Einrichtung: Department of Computer Engineering, College of Information Technology, University of Bahrain, Sakhair P.O. Box 32038, Bahrain. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning is increasingly recognized as a viable solution for deploying distributed intelligence across resource-constrained platforms, including smartphones, wireless sensor networks, and smart home devices within the broader Internet of Things ecosystem. However, traditional federated learning approaches face serious challenges in resource-constrained settings due to high processing demands, substantial memory requirements, and high communication overhead, rendering them impractical for battery-powered IoT environments. These factors increase battery consumption and, consequently, decrease the operational longevity of the network. This study proposes a streamlined, single-shot federated learning approach that minimizes communication overhead, enhances energy efficiency, and thereby extends network lifetime. The proposed approach leverages the k-nearest neighbors (k-NN) algorithm for edge-level pattern recognition and utilizes majority voting at the server/base station to reach global pattern recognition consensus, thereby eliminating the need for data transmissions across multiple communication rounds to achieve classification accuracy. The results indicate that the proposed approach maintains competitive classification accuracy performance while significantly reducing the required number of communication rounds.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencecommunication efficiencyenergy-efficient learningfederated learningin-network processinginternet of thingsmachine learningnearest neighborpattern recognitionwireless sensor networks

Autor:innen und Institutionen

  • Department of Computer Engineering, College of Information Technology, University of Bahrain, Sakhair P.O. Box 32038, Bahrain.

ORCID-Profile: M Baqer

Zitieren

APA

Baqer, M. (2025). Lightweight Federated Learning Approach for Resource-Constrained Internet of Things. Sensors, 25(18), 5633. https://doi.org/10.3390/s25185633

Vancouver

Baqer M. Lightweight Federated Learning Approach for Resource-Constrained Internet of Things. Sensors. 2025;25(18):5633. doi:10.3390/s25185633

BibTeX
@article{Baqer2025,
  author = {Baqer, M},
  title = {Lightweight Federated Learning Approach for Resource-Constrained Internet of Things},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {18},
  pages = {5633},
  doi = {10.3390/s25185633}
}
Kostenlos starten →